ArticlePublisher preview availableLiterature Review

Solar radiation and solar energy estimation using ANN and Fuzzy logic concept: A comprehensive and systematic study

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract and Figures

To overcome the need of the world for energy consumption, we have to find some better and stable alternate ways of renewable energy with advanced technology. The most readily available source of energy is solar energy but solar energy has nonlinear nature due to the random nature of climate conditions. So, one way to solve is solar radiation prediction and solar energy prediction using more accurate techniques. Also, energy business and power system control units require more accuracy along with very short to large duration prediction in advance. So, to complete the requirement many prediction techniques are used and among them, Artificial Neural Network (ANN) and Fuzzy are more accurate and reliable techniques. In this paper basically, a literature study for solar radiation and energy prediction using ANN and Fuzzy logic techniques has been carried out. Many studies are reviewed and then selected some most accurate, reliable, and relevant studies for further study. ANN models with different algorithms such as feed-forward back-propagation-based ANN, Multi-layer feed-forward-based ANN model, Linear regression with ANN model, GNN-based model are reviewed in the study. ANN models with different input parameters combinations and the different number of neurons were also reviewed. Fuzzy logic-based and Adaptive Neuro-Fuzzy interface (ANFIS)-based different models have been reviewed and observed that the ANFIS technique performs better. From the study, it has been noted that ANN and Fuzzy logic employed models are most effective for estimation than any other empirical models. It is found that solar radiation and energy prediction models are dependent on input parameters more. At last, highlighted some possible research opportunities and areas for better efficiency of the results.
This content is subject to copyright. Terms and conditions apply.
https://doi.org/10.1007/s11356-022-19185-z
REVIEW ARTICLE
Solar radiation andsolar energy estimation using ANN andFuzzy logic
concept: Acomprehensive andsystematic study
DaxalPatel1· ShriyaPatel2· PoojanPatel3· MananShah4
Received: 23 June 2021 / Accepted: 8 February 2022
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022
Abstract
To overcome the need of the world for energy consumption, we have to find some better and stable alternate ways of
renewable energy with advanced technology. The most readily available source of energy is solar energy but solar energy
has nonlinear nature due to the random nature of climate conditions. So, one way to solve is solar radiation prediction and
solar energy prediction using more accurate techniques. Also, energy business and power system control units require more
accuracy along with very short to large duration prediction in advance. So, to complete the requirement many prediction
techniques are used and among them, Artificial Neural Network (ANN) and Fuzzy are more accurate and reliable techniques.
In this paper basically, a literature study for solar radiation and energy prediction using ANN and Fuzzy logic techniques
has been carried out. Many studies are reviewed and then selected some most accurate, reliable, and relevant studies for
further study. ANN models with different algorithms such as feed-forward back-propagation-based ANN, Multi-layer feed-
forward-based ANN model, Linear regression with ANN model, GNN-based model are reviewed in the study. ANN models
with different input parameters combinations and the different number of neurons were also reviewed. Fuzzy logic-based
and Adaptive Neuro-Fuzzy interface (ANFIS)-based different models have been reviewed and observed that the ANFIS
technique performs better. From the study, it has been noted that ANN and Fuzzy logic employed models are most effective
for estimation than any other empirical models. It is found that solar radiation and energy prediction models are dependent on
input parameters more. At last, highlighted some possible research opportunities and areas for better efficiency of the results.
Keywords Solar Radiation· Solar Energy Estimation· Artificial Intelligence
Introduction
In today’s era, energy consumption is high because of the
increasing population and also energy resources are limited,
so, we have to find ways for sustainable renewable energy
resources. Renewable energy is from limitless resources and
also we can use it again and again for electricity genera-
tion. Around 1.4 billion people are lacking from electricity
in today’s modern world while 85% of them are living in
remote places. Sustainable development of renewable energy
is at the center of attraction for recent policymaking and
development plans (Owusu and Sarkodie, 2016; Lu etal.,
2015). Some major challenges for a sustainable future are
securing energy supply and curbing energy contribution dur-
ing climate change (Owusu and Sarkodie, 2016; Abbasi and
Abbasi, 2010). Coal, natural gas, and oil are some domi-
nant resources for industries because all these fossil fuel
resources are very efficient for power production but we
can’t rely on these resources for a long time because they are
limited and decrease drastically in quantity (Shahzad, 2015).
Also, Renewable Energy does not cause any greenhouse
gases and carbon dioxide (Co2), which result in climate
change. Renewable energy resources are also cost-efficient
whereas conventional resources cost is increasing turn by
Responsible Editor: Philippe Garrigues
* Manan Shah
manan.shah@spt.pdpu.ac.in
1 Department ofElectronics andCommunication Engineering,
Nirma University, Ahmedabad, Gujarat, India
2 Department ofComputer Science andEngineering, Indus
University, Ahmedabad, Gujarat, India
3 Department ofElectrical Engineering, Nirma University,
Ahmedabad, Gujarat, India
4 Department ofChemical Engineering School ofTechnology,
Pandit Deendayal Energy University, Gandhinagar, Gujarat,
India
/ Published online: 17 February 2022
Environmental Science and Pollution Research (2022) 29:32428–32442
1 3
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
... Recently, feature learning techniques based on deep learning approaches have grown in popularity (Shang et al. 2019;Petrovska et al. 2020;Shao et al. 2020;Thacker et al. 2022;Shah et al. 2022b), making handcrafted feature extraction approaches increasingly rare. The most significant feature of deep learning is its inherent property of automatically generating features (Chhajer et al. 2022;Hooda et al. 2022;Shah et al. 2022a;Patel et al. 2022). Autoencoders with encoder-decoder architecture are widely used in deep learning for feature extraction. ...
Article
Full-text available
The identification of features that can improve classification accuracy is a major concern in land cover classification research. This paper compares deep learning and transform domain feature extraction techniques for land cover classification of SAR data on balanced and imbalanced training sets. Convolutional autoencoders (CAE), variational autoencoders (VAE), and Haar wavelet transforms (HWT) are used and evaluated for feature generation capability. Variations in features of CAE and HWT help gather more information about the image patch. The fusion of CAE and HWT features provides a combination of high- and low-frequency coefficients, respectively, which improves classification accuracy for various land covers. To assess features generated through fusion of features, RISAT-1 C-band and AIRSAR L-band datasets are used. Furthermore, agricultural/grass land has similar features with open forest which leads to misclassification of forest in agricultural/grass land. Increasing the number of samples in each class using the Synthetic Minority Oversampling Technique (SMOTE) increases training samples. Hierarchical classification of the above-mentioned features, where agricultural/grass land and forest classes are discriminated, improves classification results. This paper evaluates all the three types of features and fused features and provides a guidance for land cover classification.
... Hence, improving the accuracy and reliability of short-term LPD forecasts are crucial for the safety of grid system operation and management. Machine learning (ML) techniques have been broadly introduced in power load forecasts (Meira et al. 2021;Sun et al. 2022) and time series forecasts (Khan et al. 2020;Hossain Lipu et al. 2021;Patel et al. 2022;Belmahdi et al. 2022;Xu et al. 2022a, b), mainly engaging point forecasts, interval predictions, and probability density forecasts (Ibrahim et al. 2020;Wen and Yuan 2020;Zhang et al. 2021;Zhang and Chen 2022;Zhang and Wang 2022;Liu et al. 2022). Point forecasting, the most frequently used technique, can provide a point estimate of the future load for each forecast horizon. ...
Article
Full-text available
Energy efficiency is crucial to greenhouse gas (GHG) emissions pathways reported by the Intergovernmental Panel on Climate Change. Electrical overload frequently occurs and causes unwanted outages in distribution networks, which reduces energy utilization efficiency and raises environmental risks endangering public safety. Electrical load, however, has a dynamically fluctuating behavior with notoriously nonlinear hourly, daily, and seasonal patterns. Accurate and reliable load forecasting plays an important role in scheduling power generation processes and preventing electrical systems from overloading; nevertheless, such forecasting is fundamentally challenging, especially under highly variable power load and climate conditions. This study proposed a deep learning-based Monotone Composite Quantile Regression Neural Network (D-MCQRNN) model to extract the multiple non-crossing and nonlinear quantile functions while conquering the drawbacks of error propagation and accumulation encountered in multi-step-ahead probability density forecasting. The constructed models were assessed by an hourly power load series collected at the electric grid centre of Henan Province in China in two recent years, along with the corresponding meteorological data collected at 16 monitoring stations. The results demonstrated that the proposed D-MCQRNN model could significantly alleviate the time-lag and biased-prediction phenomena and noticeably improve the accuracy and reliability of multi-step-ahead probability density forecasts on power load. Consequently, the proposed model can significantly reduce the risk and impact of overload faults and effectively promote energy utilization efficiency, thereby mitigating GHG emissions and moving toward cleaner energy production.
... Many artificial neural networks (ANNs) are employed in the solution of issues such as pattern matching and data compression. As a promising and rising technology, artificial neural networks (ANNs) have emerged as a popular tool for forecasting and prediction [31,32]. ...
Article
Full-text available
This study looks into artificial intelligence methods for scaling solar power systems, such as standalone, grid-connected, and hybrid systems, in order to lessen environmental effect. When all essential information is provided, conventional sizing methods may be a feasible alternative. It is impossible to apply typical procedures in instances where data is unavailable. The new suggested artificial intelligence model employing multilayered perceptrons is employed for sizing solar systems, and this model functions on current photovoltaic modules that incorporate hybrid-sizing models; so, they should not be rejected entirely. In this work, the convergence speed of the proposed model for single diode, two diodes, and three diodes are the comparison factors to estimate the performance of the proposed model.
Article
Full-text available
Recent developments in solar equipment's have motivated researchers to formulate an accurate measurement system for solar radiation under varying environment circumstances that could prove to be economical and viable. To furnish precise estimators of solar radiation, multiple models of different background are employed which are capable of solving complex non-linear data collection and processing problems. These models are immensely proficient in predicting solar radiation by means of numerous algorithms for different functions. Current research compares the prediction capability of several prediction models on various criteria's such as accuracy, cost, time and skill requirement. The present study is accomplished in New Delhi, India using hybrid combination of two Multi Criteria Estimators methods. Weights were calculated by Analytical Hierarchical Process and assigned to each performance attribute. Accuracy is the most significant attribute as its percentage contribution is the maximum (48.28%) followed by skill requirement (31.38%), time (14.41%), and cost (5.9%). Furthermore, the research then ranks these models on the basis of their attributes with the aid of Technique for Order Preference by Similarity to Ideal Solution. Among all these models, Artificial Neural Network model was ranked as the best model for its application in the field of solar energy, followed very closely by Support Vector Machine model while Response Surface Methodology came out to be least favourite.
Article
Full-text available
With climate change driving an increasingly stronger influence over governments and municipalities, sustainable development, and renewable energy are gaining traction across the globe. This is reflected within the EU 2030 agenda, that envisions a future where there is universal access to affordable, reliable and sustainable energy. One of the challenges to achieve this vision lies on the low reliability of certain renewable sources. While both particulars and public entities try to reach self-sufficiency through sustainable energy generation, it is unclear how much investment is needed to mitigate the unreliability introduced by natural factors such as varying wind speed and daylight across the year. In this sense, a tool that aids predicting the energy output of sustainable sources across the year for a particular location can aid greatly in making sustainable energy investments more efficient. In this paper, we make use of Open Data sources, Internet of Things (IoT) sensors and installations distributed across Europe to create such tool through the application of Artificial Neural Networks. We analyze how the different factors affect the prediction of energy production and how Open Data can be used to predict the expected output of sustainable sources. As a result, we facilitate users the necessary information to decide how much they wish to invest according to the desired energy output for their particular location. Compared to state-of-the-art proposals, our solution provides an abstraction layer focused on energy production, rather that radiation data, and can be trained and tailored for different locations using Open Data. Finally, our tests show that our proposal improves the accuracy of the forecasting, obtaining a lower mean squared error (MSE) of 0.040 compared to an MSE 0.055 from other proposals in the literature.
Article
Full-text available
With the characteristics of high-speed calculation and high-accuracy prediction, artificial intelligence (AI) which also known as machine intelligence, including deep learning, machine learning, etc., have shown great advantages in cross-field applications. In material science field, AI can be used to discover new materials and predict corresponding critical properties. At present, AI has been used in the exploitation of energy conversion materials and other energy-related materials. In this review, we summary the current achievements of AI applications in energy conversions, analyze the advantages and disadvantages of AI techniques in material researches and point out future development prospects.
Article
Full-text available
Internet of things is an emerging technology that efficiently and effectively improving our daily life activities. It reducing the cost of living by automating the manual processes. It integrates physical objects and devices via internet for synchronized communication. Currently the cost of electricity is reaching the sky so we need some sources that can produce electricity naturally without any cost. Here, solar panels and solar plants take place for producing electricity in natural manner with sun light. Photo voltaic cells are used in these systems that converts the sun light into electricity. Mostly the solar systems are configured in rural or agricultural areas where electricity mediums are still not available. These systems are manually operated by humans. So there is need of efficient approach which automatically control and monitor the current, voltage and other parameters of solar systems and provides real time statistics to users. This research paper proposes an IOT based approach for solar power consumption and monitoring that allow the users to monitor or control a solar plant their mobiles. Majorly, solar plants are built in the locations where people cannot reach on daily basis so this approach allows the people to virtually control their systems from faraway places.
Article
Full-text available
The paper provides an overview of how Artificial Intelligence (AI) is applied in different government sectors. Our methodology is based on a systematic review of 74 papers retrieved from Web of Science and Scopus databases. We find that the extant literature is less focused on healthcare, ICT, education, social and cultural services, and fashion sector; while ignoring the practical implementation of AI in these sectors. We present an organizing framework stating different areas related to governance and throws light on research gaps in the extant literature that can be further worked upon for promoting the research in digital governance.
Article
Full-text available
The biggest renewable energy sources in Indonesia is solar energy. The installed capacity of Solar Power System in 2017 is still very far from the target. Solar radiation is very infulental on the photovoltaic performance in generating energy. The need for solar radiation estimation has become important in the design of photovoltaic system. Previous research has been done using Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy (ANFIS) methods. In this research, Genetic Algorithm Modified Fuzzy (GAMF) method used to estimate the solar radiation. Meteorogical dates used in this research are temperature, humidity, wind velocity and wind direction. There are 2 types of datas that are BMKG data and measurement data. Three experimental variations of input variation were performed for each data. For BMKG data the best estimation result is obtained when using humidity, temperature and wind velocity as variation inputs with RMSE and MAE of 145.19 and 72. While for the best result estimation result data obtained when applying humidity, temperature, wind speed and wind direction as variation inputs with values of RMSE and MAE were 1.44 and 0.65.
Article
Full-text available
Solar energy is the most popular resource for power generation among the various available renewable energy alternatives. Solar radiation data are important for solar photovoltaic (PV) systems and passive energy-efficient building designs. Due to the unavailability of measurement in rural locations, solar radiation prediction models are required. In recent years, the Artificial Neural Networks (ANN) were successfully used for predicting solar radiation. However, previous works indicated that the ANN techniques were mainly focusing on prediction of monthly average or daily solar radiation, a few of them were modelled for predicting solar irradiance in hourly basis. In this study, prediction models of global solar irradiance on a horizontal surface will be developed based on neural-network techniques. Hourly meteorological variables between 2012 and 2015 acquired from the measurements made by local meteorological station were used for the study. To consider the effectiveness of individual predictors, different combinations of input variables were analysed using the Levenberg-Marquardt (LM) algorithm. Finally, equations were modelled by regression based on the important predictors. The developed models were used to estimate the global irradiance and assessed against measurement results.
Chapter
Artificial intelligence (AI) techniques are becoming useful as alternate approaches to conventional techniques or as components of integrated systems. They have been used to solve complicated practical problems in various areas and nowadays are very popular. They are widely accepted as a technology offering an alternative way to tackle complex and ill-defined problems. They can learn from examples, are fault tolerant in the sense that they are able to handle noisy and incomplete data, are able to deal with non-linear problems and once trained can perform prediction and generalization at very high speed. AI-based systems are being developed and deployed worldwide in a wide variety of applications, mainly because of their symbolic reasoning, flexibility and explanation capabilities. They have been used in diverse applications in control, robotics, pattern recognition, forecasting, medicine, power systems, manufacturing, optimization, signal processing and social/psychological sciences. They are particularly useful in system modeling such as in implementing complex mappings and system identification. This chapter presents a review of the main AI techniques such as expert systems, artificial neural networks, genetic algorithms, fuzzy logic and hybrid systems, which combine two or more techniques. It also outlines some applications in the energy sector.
Conference Paper
The research aims to develop a prediction system of solar energy radiation in the tropical region for home energy needs. The tropics get sunlight all year round. The Solar energy radiates abundantly in the tropic. The Solar radiation Energy is influenced by weather factors. The input data in this study use weather factors such mximum temperature, minimum temperature, Precipitation, wind speed and relative humidity. The input data retrieves in 3 regions are Klaten, Sragen and Sukoharjo. The prediction system was built by using soft computing. The method used in this prediction system is an adaptive neuro fuzzy inference system (ANFIS) using hybrid Hybrid optimization method was chosen because it produces a calculation of RMSE (root mean square error) which is lower than backpropagation. methods. Hybrid optimization method was chosen because it produces a calculation of RMSE (root mean square error) which is lower than backpropagation. The prediction results were the values of solar energy in each region.